公开(公告)号：WO2008076511A2

公开(公告)日：2008-06-26

申请号：PCT/US2007/082314

申请日：2007-10-24

Applicant: MOTOROLA, INC. ,  ZHOU, James Kefeng ,  HAUSE, Leonard C.

Inventor： ZHOU, James Kefeng ,  HAUSE, Leonard C.

IPC: H04M1/00

CPC classification number: H04M1/6016 ,  H04M3/56 ,  H04M3/568 ,  H04M2201/41 ,  H04M2250/62

Abstract: A method and system for managing a communication session is provided. The communication session is associated with multiple communication devices. The method includes learning (304) a set of derived acoustic features of an audio communication signal that is associated substantially only with one user of a communication device. The method also includes receiving (306) a communication session signal. The communication session signal is an audio signal that includes a combination of audio communication signals. Each audio communication signal of the audio communication signals is associated with a user of a communication device of the multiple communication devices. The method includes modifying (308) the communication session signal based on the set of derived acoustic features.

Abstract translation: 提供了用于管理通信会话的方法和系统。 通信会话与多个通信设备相关联。 该方法包括学习（304）基本上仅与通信设备的一个用户相关联的音频通信信号的一组派生声学特征。 该方法还包括接收（306）通信会话信号。 通信会话信号是包括音频通信信号的组合的音频信号。 音频通信信号的每个音频通信信号与多个通信设备中的通信设备的用户相关联。 该方法包括基于该组派生声学特征修改（308）通信会话信号。

公开(公告)号：WO2007146084A2

公开(公告)日：2007-12-21

申请号：PCT/US2007/013451

申请日：2007-06-06

Applicant: CISCO TECHNOLOGY, INC. ,  SHAFFER, Shmuel ,  JAIN, Mukul ,  KUMAR, Sanjeev ,  PATEL, Labhesh

Inventor： SHAFFER, Shmuel ,  JAIN, Mukul ,  KUMAR, Sanjeev ,  PATEL, Labhesh

IPC: H04M1/64

CPC classification number: H04M3/53366 ,  H04M3/385 ,  H04M2201/39 ,  H04M2201/41 ,  H04M2203/4554

Abstract: Techniques and systems for recalling voicemail messages from remote voicemail systems are disclosed. In one embodiment, a method for recalling a voicemail message from a target mailbox can include: accessing a voicemail system by a caller using a device; authenticating the caller using speaker verification; and deleting the voicemail message from the target mailbox. The target mailbox owner can be a member of the voicemail system, while the caller can be a non-member of that voicemail system. The device may be configured to support a telephony user interface (TUI), for example.

Abstract translation: 公开了用于从远程语音邮件系统调用语音邮件消息的技术和系统。 在一个实施例中，用于从目标邮箱调用语音邮件消息的方法可以包括：由呼叫者使用设备访问语音邮件系统; 使用说话人验证认证来电者; 并从目标邮箱中删除该语音邮件消息。 目标邮箱所有者可以是语音信箱系统的成员，而呼叫者可以是该语音邮件系统的非成员。 该设备可以被配置为支持例如电话用户界面（TUI）。

公开(公告)号：WO2007001452A2

公开(公告)日：2007-01-04

申请号：PCT/US2005/040853

申请日：2005-11-10

Applicant: AMERICAN EXPRESS MARKETING & DEVELOPMENT CORP. ,  KOHR, Chin, H. ,  LEYVA, Marcel ,  MARSHALL, Vernon

Inventor： KOHR, Chin, H. ,  LEYVA, Marcel ,  MARSHALL, Vernon

IPC: G06F17/00

CPC classification number: H04M3/5175 ,  G06Q30/016 ,  G06Q30/02 ,  G10L17/00 ,  G10L17/02 ,  G10L17/26 ,  G10L25/48 ,  G10L25/63 ,  H04M3/2281 ,  H04M3/51 ,  H04M2201/18 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/301 ,  H04M2203/401

Abstract: One-to-many comparisons of callers' words and/or voice prints with known words and/or voice prints to identify any substantial matches between them. When a customer communicates with a particular entity, such as a customer service center, the system makes a recording of the real-time call including both the customer's and agent's voices. The system segments the recording to extract different words, such as words of anger. The system may also segment at least a portion of the customer's voice to create a tone profile, and it formats the segmented words and tone profiles for network transmission to a server. The server compares the customer's words and/or tone profiles with multiple known words and/or tone profiles stored on a database to determine any substantial matches. The identification of any matches may be used for a variety of purposes, such as providing representative feedback or customer follow-up.

Abstract translation: 一对多呼叫者的单词和/或语音打印与已知的单词和/或语音打印进行比较，以识别它们之间的任何实质的匹配。 当客户与特定实体（例如客户服务中心）通信时，系统记录实时呼叫，包括客户和代理人的声音。 系统分割录音以提取不同的单词，如愤怒的话。 该系统还可以划分客户语音的至少一部分以创建音调简档，并且将用于网络传输的分段单词和音调配置文件格式化成服务器。 服务器将客户的单词和/或音调配置文件与存储在数据库上的多个已知单词和/或音调配置文件进行比较，以确定任何实质的匹配。 任何比赛的识别可以用于各种目的，例如提供代表性反馈或客户跟进。

公开(公告)号：WO2006126183A2

公开(公告)日：2006-11-30

申请号：PCT/IL2006000110

申请日：2006-01-26

Applicant: NICE SYSTEMS LTD ,  WASERBLAT MOSHE ,  EILAM BARAK ,  PEREG OREN ,  KOR ILAN

Inventor： WASERBLAT MOSHE ,  EILAM BARAK ,  PEREG OREN ,  KOR ILAN

IPC: H04M15/00

CPC classification number: H04M3/36 ,  G06Q20/4016 ,  G10L17/26 ,  H04M3/385 ,  H04M2201/41 ,  H04M2203/6027

Abstract: An apparatus and method for detecting a fraud or fraud attempt in a captured interaction. The method comprising a selection step in which interactions suspected as capturing fraud attempts are selected for further analysis, and assigned a first fraud probability, and a fraud detection step in which the voice is scored against one or more voice prints, of the same alleged customer or of known fraudsters. The first fraud or fraud attempt probability is combined with the result of the scoring of the fraud detection step, to generate a total fraud or fraud attempt probability. If the total fraud or fraud attempt probability exceeds a threshold, a notification is issued. The selection, scoring and combination thereof are performed using user-defined rules and thresholds.

Abstract translation: 一种用于检测捕获的交互中的欺诈或欺诈尝试的装置和方法。 所述方法包括选择步骤，其中选择被怀疑为捕获欺诈尝试的交互用于进一步分析，并且分配了第一欺诈概率，以及欺诈检测步骤，其中所述语音针对相同的所述客户的一个或多个语音打印 或已知的欺诈者。 将第一个欺诈或欺诈尝试概率与欺诈检测步骤的评分结果相结合，以产生总的欺诈或欺诈尝试概率。 如果总欺诈或欺诈尝试概率超过阈值，则发出通知。 使用用户定义的规则和阈值来进行选择，评分和组合。

公开(公告)号：WO2006089822A1

公开(公告)日：2006-08-31

申请号：PCT/EP2006/050308

申请日：2006-01-19

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  JARAMILLO, David ,  MCCOBB, Gerald

Inventor： JARAMILLO, David ,  MCCOBB, Gerald

IPC: G06F21/00

CPC classification number: G10L17/22 ,  G06F21/32 ,  G10L17/00 ,  H04M3/385 ,  H04M2201/41

Abstract: A method of verifying a user identity using a Web-based multimodal interface can include sending, to a remote computing device, a multimodal markup language document that, when rendered by the remote computing device, queries a user for a user identifier and causes audio of the user's voice to be sent to a multimodal, Web-based application. The user identifier and the audio can be received at about a same time from the client device. The audio can be compared with a voice print associated with the user identifier. The user at the remote computing device can be selectively granted access to the system according to a result obtained from the comparing step.

Abstract translation: 使用基于Web的多模式接口验证用户身份的方法可以包括向远程计算设备发送多模式标记语言文档，所述多模式标记语言文档在由远程计算设备呈现时向用户查询用户标识符并导致 将用户的语音发送到多模式的基于Web的应用程序。 可以在大约相同的时间从客户端设备接收用户标识符和音频。 音频可以与与用户标识符相关联的语音打印进行比较。 可以根据从比较步骤获得的结果，选择性地授予对远程计算设备的用户对系统的访问。

公开(公告)号：WO2004012387A1

公开(公告)日：2004-02-05

申请号：PCT/AU2003/000978

申请日：2003-07-31

Applicant: TOMS, David

Inventor： TOMS, David

IPC: H04L9/32

CPC classification number: G10L17/22 ,  G10L17/00 ,  H04M1/67 ,  H04M3/2218 ,  H04M3/2281 ,  H04M3/36 ,  H04M3/42059 ,  H04M2201/18 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/6027 ,  H04M2207/206

Abstract: A system is provided for the automatic detection of fraudulent activity on a transaction network, wherein each transaction has an associated identifier. The system includes voice comparison means (32) for comparing a first sampled voice of a user of a first transaction with a subsequently sampled voice of a user of a subsequent transaction having an identical identifier to that of the first transaction. Control means in the form of a fraud detection engine (26) is provided for determining, from said comparison, a profile of user usage that is representative of a total number of different users of the associated identifier. The fraud detection engine is configured to compare the profile of user usage with a threshold for fraudulent use, and to generate a fraud condition signal (40) in the event that the profile exceeds said threshold. If required, the fraud condition signal may be provided to automatically terminate the fraudulent transaction.

Abstract translation: 提供了一种用于自动检测交易网络上的欺诈活动的系统，其中每个交易具有相关联的标识符。 该系统包括语音比较装置（32），用于将第一交易的用户的第一采样语音与具有与第一交易的相同标识符的后续交易的用户的后续采样语音进行比较。 提供了欺诈检测引擎（26）形式的控制装置，用于从所述比较中确定代表相关标识符的不同用户总数的用户使用情况。 欺诈检测引擎被配置为将用户使用情况的简档与欺诈性使用的阈值进行比较，并且在配置文件超过所述阈值的情况下生成欺诈条件信号（40）。 如果需要，可以提供欺诈条件信号以自动终止欺诈交易。

公开(公告)号：WO2002069325A1

公开(公告)日：2002-09-06

申请号：PCT/US2002/006133

申请日：2002-02-26

Applicant: STARTOUCH INTERNATIONAL, LTD. ,  ROHWER, Elizabeth, A.

Inventor： ROHWER, Elizabeth, A.

IPC: G10L17/00

CPC classification number: H04M7/006 ,  G10L15/22 ,  G10L15/30 ,  H04M2201/41 ,  H04M2201/42

Abstract: Human speech is transported through a voice and data converged Internet network to recognize its content, verify the ifentity of the speaker, or to verify the content of a spoken phrase by utilizing the Internet protocol to transmit voice packets. The voice data (4) entered is processed and transmitted in the same way as Internet data packets over converged voice and data IP networks. A voice-enabled application isends a message (5), which is decoded by the speech API (2) and the appriopriate control and synchronization information is issued (7) to the data preparation module (9) and to the speech engine (3). Standard voice over IP includes a speech compression algorithm and the use of RTP (Real Time Protocol), enabling additional processing of the human voice anywhere in the network to perform speaker verification, with or without the knowledge of the speaker.

Abstract translation: 通过语音和数据融合的互联网网络传输人类语音，以识别其内容，验证说话者的真实性，或者通过利用因特网协议传输语音数据包来验证口头短语的内容。 输入的语音数据（4）以与互联网数据包相同的方式通过融合的语音和数据IP网络进行处理和传输。 支持语音的应用程序发出消息（5），该消息由语音API（2）解码，向数据准备模块（9）和语音引擎（3）发出适当的控制和同步信息（7） 。 标准IP语音包括语音压缩算法和RTP（实时协议）的使用，能够在或不用说话者的知识的情况下在网络中的任何地方进行人声的附加处理来执行说话者验证。

公开(公告)号：WO01050455A1

公开(公告)日：2001-07-12

申请号：PCT/EP2000/012850

申请日：2000-12-15

IPC: G10L17/04 ,  G10L17/24 ,  G10L17/00

CPC classification number: G10L17/04 ,  G10L17/24 ,  H04M3/42059 ,  H04M2201/41

Abstract: The invention relates to a method for the voice-operated identification of the user of a telecommunication line in a telecommunications network during an interactive communication using a voice-operated conversational system. According to the invention, during a person-to-person and/or person-to-machine conversation, the verbal expressions of a caller in a group of callers that is restricted to a telecommunication line are used to create a reference pattern for the user. A user identification is stored for each reference pattern. Said identification is activated after recognition of the user and, together with the CLI or ANI, is made available to a server with a voice-operated conversational system. Data for this user, which has already been saved using the CLI with user identification is determined by the system and made available for the interaction with the client. The inventive method can be advantageously used in voice-operated conversational systems.

Abstract translation: 本发明的具有语音控制对话系统一个对话期间涉及一种用于在电信网络中电信终端的用户的语音控制识别的方法。 根据本发明的对话个人对个人和/或人对机器期间呼叫方，一个限制到电信终端组的呼叫者的发明话语被用来创建呼叫者的参考图案。 的用户ID被存储用于每个参考图案中，检测呼叫者的与CLI或电信终端的ANI识别在一起之后被激活被提供给一个语音服务器对话系统。 系统已经通过用户ID使用CLI为这个用户存储的数据来确定和进行与客户的对话提供。 本发明的方法可用于语音控制的对话系统优选。

公开(公告)号：WO9747122A3

公开(公告)日：1998-01-22

申请号：PCT/US9709103

申请日：1997-05-30

Applicant: WORLDVOICE INC ,  FINNIGAN PAUL F

Inventor： FINNIGAN PAUL F

IPC: H04M3/487 ,  H04M3/50 ,  H04M3/533

CPC classification number: H04M3/53366 ,  G10L17/00 ,  H04M3/42042 ,  H04M3/42059 ,  H04M3/42093 ,  H04M3/42102 ,  H04M3/487 ,  H04M3/533 ,  H04M3/53325 ,  H04M3/53383 ,  H04M2201/40 ,  H04M2201/41

Abstract: Authentication of voice message recipient network addresses employs generating (102) and storing (104) a 'network file' that includes 'voice clips' and associated network addresses that are extracted from voice messages received across a network (10) from voice message systems (16, 18). A voice clip is the first one to three seconds of voice extracted from each received voice message. Over time, the network file will grow to contain multiple voice clips and associated network voice message addresses. When a voice message originator subsequently enters a recipient's network address (106), the originating voice message system searches (114) the network file for the network address, retrieves the associated voice clip (116), and plays it for the voice message originator to authenticate the recipient's network address. Voice authentication of a voice message originator entails encoding (134) into a 'voice print file', original voice clips and associated network addresses received from positively identified voice message originators. Thereafter, when a questionable voice message is received (138), the voice message system extracts a new voice clip (142), generates a new voice print (144), and compares it with the original voice print associated with the voice message address (148). If the voice prints are substantially the same, the received voice message is annotated with an 'authenticating' message (150).

公开(公告)号：WO1997001932A1

公开(公告)日：1997-01-16

申请号：PCT/US1996010884

申请日：1996-06-27

Applicant: AT & T CORP.

Inventor： AT & T CORP. ,  BRUNO, Richard, F. ,  GIBBON, David, C. ,  KATSEFF, Howard, P. ,  MARKOWITZ, Robert, E. ,  ROBINSON, Bethany, S. ,  SHAHRARAY, Behzad ,  STUNTEBECK, Peter, H. ,  WEBER, Roy, P.

IPC: H04N07/15

CPC classification number: H04M3/42221 ,  H04M3/567 ,  H04M2201/41 ,  H04N7/142 ,  H04N7/147 ,  H04N7/15 ,  H04N7/152

Abstract: A method and apparatus for recording and indexing audio information exchanged during an audio conference call, or video, audio and data information exchanged during a multimedia conference. For a multimedia conference, the method and apparatus utilize the voice activated switching functionality of a multipoint control unit (MCU) (26) to provide a video signal, which is input to the MCU (26) from a workstation from which an audio signal is detected, to each of the other workstations participating in the conference. A workstation and/or participant-identifying signal generated by the multipoint control unit (26) is stored, together or in correspondence with the audio signal and video information, for subsequent ready retrieval of the stored multimedia information. For an audio conference, a computer (32') is connected to an audio bridge (44) for recording the audio information along with an identification signal for correlating each conference participant with that participant's statements.

Abstract translation: 一种用于在音频电话会议期间交换的音频信息或在多媒体会议期间交换的视频，音频和数据信息的记录和索引的方法和装置。 对于多媒体会议，该方法和装置利用多点控制单元（MCU）（26）的语音激活切换功能来提供视频信号，该视频信号从一个工作站输入到MCU（26），一个音频信号是 检测到参加会议的其他工作站。 由多点控制单元（26）生成的工作站和/或参与者识别信号一起或与音频信号和视频信息对应地存储，以便随后检索存储的多媒体信息。 对于音频会议，计算机（32'）连接到音频桥（44），用于记录音频信息以及用于使每个会议参与者与该参与者的语句相关联的识别信号。